Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/inetgas/arch-compiler/using-arch-compilernpx skills add inetgas/arch-compiler --skill using-arch-compilergit clone --depth 1 https://github.com/inetgas/arch-compilerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/inetgas/arch-compiler/using-arch-compiler)<a href="https://agentmods.dev/skills/inetgas/arch-compiler/using-arch-compiler"><img src="https://agentmods.dev/badge/skills/inetgas/arch-compiler/using-arch-compiler.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.00636 |
| Opus 5 | $0.00015 | $0.00318 |
| Sonnet 5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
using-arch-compiler scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Architecture Compiler
Read This First
Before doing anything else:
- Read
AGENTS.md. - Treat
tools/,schemas/,config/, andpatterns/as read-only unless the human explicitly asked for compiler-maintenance work in this repo. - Decide whether the task is about architecture selection or architecture implementation.
Routing Rule
Use skills/compiling-architecture/SKILL.md when:
- the user wants to turn requirements into architecture decisions
- the user wants to write or refine a spec
- the user wants to compile, recompile, inspect pattern selection, or finalise an architecture
- the user has an existing prototype or codebase and needs to compile, validate, or re-approve the architecture it should converge to
docs/architecture/does not exist yetdocs/architecture/architecture.yamlis missing approval- implementation planning or coding exposes unresolved provider/runtime/auth/retention/message-path decisions
- any later decision would change
constraints.*,constraints.saas-providers, top-levelpatterns.*, or accepted risk posture - the user wants existing prototype choices to replace approved providers, boundaries, or selected patterns
Use skills/implementing-architecture/SKILL.md when:
docs/architecture/architecture.yamlexists- it is approved
- the task is to write code that follows that architecture
- the task is to refactor an existing prototype or codebase so it conforms to the approved architecture
- provider/runtime bindings are already concrete enough that coding will not silently replace the approved contract
Hard Stops
- If the full Architecture Compiler repo is not installed in a stable local path, stop and install it before routing further. Installing only copied skill files is not enough; the workflows depend on
tools/,schemas/,config/, andpatterns/. - If no application repo exists yet, do not write app architecture artifacts into the compiler repo.
- If an implementation task lacks approved architecture, stop and switch to the compiling skill.
- If planning starts under the implementing skill and reveals unresolved architecture-binding choices, stop and route back to the compiling skill before more planning or coding.
- If a previously approved architecture is recompiled or materially changed, treat the old approval as invalid until the human re-approves the new output.
- If the user is asking to change compiler behavior or the pattern registry itself, this is compiler-maintenance work, not normal skill usage.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 55 lines · 30 tokens per session scan A c176e102f816
using-arch-compiler is a skill published in the GitHub repository inetgas/arch-compiler (10 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 636 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
deploy-registry-server-with-cnpg
Deploy the ToolHive Registry Server to a Kind cluster with CloudNativePG (CNPG) PostgreSQL database. Use when you need a production-like PostgreSQL setup with the CNPG operator.
deploy-registry-server-with-otel
Deploy the ToolHive Registry Server to a Kind cluster with telemetry enabled. Use when you need to deploy the registry server for testing with OTEL metrics and tracing.
classification-at-scale
Classify an internal catalog against a standard taxonomy at scale using deterministic providers, tri-state signals, batch group review, and a trust flywheel — LLM judgment only for configs, ambiguous tails, and critique.
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
create-state
Create a new Cruxible state from raw domain data through staged graph, workflow, query, and review-loop design.